gistfile1.py

#!/usr/bin/python2
# -*- coding: utf-8 -*-
import SimpleHTTPServer
import SocketServer
import signal
import sys
import urllib2
import gzip
import zlib
import webbrowser
import os
from bs4 import BeautifulSoup
from bs4.element import NavigableString
from StringIO import StringIO


port = 8000


def get_url_data(url):
    """Gets data y by pointed url.
    :url: str
    :return: str
    """
    res = urllib2.urlopen(url)
    data = None
    if res.info().get('Content-Encoding') == 'gzip':
        buf = StringIO(res.read())
        f = gzip.GzipFile(fileobj=buf)
        data = f.read()
        f.close()
    else:
        data = res.read()

    return data


def interpret_data(data):
    """Interprets data by pointer task.
    :type data: unicode
    """
    out_soup = BeautifulSoup()
    soup = BeautifulSoup(data)
    counter = 1

    for item in soup.find_all(True):
        strings = filter(lambda x: type(x) == NavigableString, item.contents)
        if (item.name not in ('script', 'noscript', 'style',) and
                len(strings)):
            i = 0
            for string in strings:
                words = string.split(' ')

                j = counter
                for word in words:
                    if len(word.strip()):
                        if counter % 6 == 0:
                            word += u'™'
                            words[counter - j] = word
                        counter += 1

                string.replace_with(' '.join(words))
                i += 1

        elif item.name in ('script', 'link',):
            path = None
            key = 'src' if item.name == 'script' else 'href'
            path = item.attrs.get(key, None)

            if path and path.find('/') == 0:
                item.attrs[key] = 'http://habrahabr.ru'+path

    # Edits links on page.
    for item in soup.find_all('a'):
        if 'href' in item.attrs:
            item.attrs['href'] = item.attrs['href'].replace(
                'http://habrahabr.ru/', 'http://localhost:%s/' % port)
    return soup


class MyHandler(SimpleHTTPServer.SimpleHTTPRequestHandler):
    def get_habradata(self):
        url = u'http://habrahabr.ru%s' % self.path
        data = get_url_data(url)
        soup = interpret_data(data)
        return soup

    def do_GET(self):
        self.send_response(200, 'OK')
        self.send_header('Content-type', 'text/html; charset=utf8')
        self.end_headers()
        res = self.get_habradata()
        self.wfile.write(res)


def main():
    if sys.argv[1:]:
        # I know that it is bad practice.
        global port
        port = int(sys.argv[1])

    webbrowser.open_new_tab('http://localhost:%s' % port)
    httpd = SocketServer.TCPServer(('127.0.0.1', port), MyHandler)
    httpd.serve_forever()


if __name__ == '__main__':
    main()